Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3599 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.2455. Min Act: -0.1700
Data Index: 523493 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.2142. Min Act: -0.1700
Data Index: 3857662 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.2142. Min Act: -0.1700
Data Index: 823311 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.1830. Min Act: -0.1700
Data Index: 5513768 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.1517. Min Act: -0.1700
Data Index: 8560596 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0892. Min Act: -0.1700
Data Index: 4380072 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.1205. Min Act: -0.1700
Data Index: 6720825 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.1205. Min Act: -0.1700
Data Index: 3565722 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0892. Min Act: -0.1700
Data Index: 2565183 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.1205. Min Act: -0.1700
Data Index: 3606144 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0892. Min Act: -0.1700
Data Index: 4050858 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0892. Min Act: -0.1700
Data Index: 6457571 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.1205. Min Act: -0.1700
Data Index: 8696920 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0580. Min Act: -0.1700
Data Index: 2416585 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0580. Min Act: -0.1700
Data Index: 8554937 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0580. Min Act: -0.1700
Data Index: 7557765 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0580. Min Act: -0.1700
Data Index: 7073266 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0580. Min Act: -0.1700
Data Index: 4133678 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0267. Min Act: -0.1700
Data Index: 952855 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2455. Min Range: -5.2455
Max Act: 5.0580. Min Act: -0.1700
Data Index: 6706408 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19